© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3020
    Prev
    Next
    INDEX
    Explanations

    distribution and uniformity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ļç§įå½¢å¼ı
    -0.10
    Ñĥг
    -0.08
    odor
    -0.08
    toolbox
    -0.08
    auge
    -0.08
    ç»ıæµİæķĪçĽĬ
    -0.08
    ftware
    -0.08
    angelo
    -0.08
    æĭĦ
    -0.08
    ì¼ĵ
    -0.08
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.13
    ness
    0.13
    -ish
    0.10
     distribution
    0.10
     DISTRIBUT
    0.09
    大纲
    0.09
    æªĶ
    0.09
    emente
    0.09
    -sided
    0.09
    ently
    0.09
    Activations Density 0.035%

    No Known Activations